Name: Arvind Mohan
Pronouns:
Biography:
Dr. Arvind T. Mohan is a Staff Scientist in the Computational Physics and Methods group at Los Alamos National Laboratory. He obtained his PhD in Aeronautical and Astronautical Engineering from The Ohio State University with research in Computational Fluid Dynamics, data-driven aerodynamics and stall failure for aircraft wings. His current research is focused on learning surrogate models and PDEs in turbulent flow and earth sciences, with a focus on critical systems such as climate impacts and nuclear applications.
Institution/Lab: Los Alamos National Laboratory
Website: https://scholar.google.com/citations?user=kr8XW9oAAAAJ&hl=en
SRP Collaboration Topic/Title: Machine Learning for Surrogate Modeling in Earth Sciences
Field or research area: Machine Learning and Physical Sciences
Please select all the topical areas that apply to your project:
Computational Science Applications (i.e., bioscience, cosmology, chemistry, environmental science, nanotechnology, climate, etc.); Machine Learning and AI
Brief Abstract:
Climate change is already causing more frequent and severe extreme weather events, such as hurricanes, floods, droughts, and wildfires. These events can have devastating impacts on communities, livelihoods, and infrastructure. Machine learning has become an attractive alternative to developing fast surrogate models of these phenomena. ML surrogate models can help decision-makers better understand and respond to these events and mitigate their consequences. To be valid, these models need to a) Predict the likelihood and severity of future climate disasters and b) Assess the vulnerability of communities and infrastructure to climate disasters. c) Be robust and reliable for trustworthiness. However, there are many fundamental challenges to making ML models helpful in this area, and the summer project will focus on developing methods to address this issue. The topic is open-ended, and the student will have the opportunity to pick a specific direction of their liking.
Desired relevant skills, background, or interests:
1) Experience and knowledge of fluid mechanics and turbulence. 2) Good understanding of partial and ordinary differential equations 3) Experience with neural networks is desired.
Other comments:
Do any special requirements apply? In-Person Only; Permanent Resident OK; International OK
Other, specify:
Keywords:
Machine Learning, Digital Twins, Earth Sciences
Lightning Talk Title: “AI-enabled” Surrogate PDE models